Relationships of swarm intelligence and artificial immune system Online publication date: Wed, 03-Apr-2013
by Renbin Xiao; Tinggui Chen
International Journal of Bio-Inspired Computation (IJBIC), Vol. 5, No. 1, 2013
Abstract: Swarm intelligence (SI) and artificial immune system (AIS) are both derived from imitation of nature biology system. Their common characteristic is that they both have simple individuals but appear emergence characteristic in population level through interaction among individuals. In order to explore inherent similarity and difference of complex system, we take two typical forms of swarm intelligence (ant colony system and particle swarm optimisation), and AIS as objectives to study this characteristic in this paper. First, we discuss the similarity between two biology systems from system structure and operation mechanism. In addition, we also illustrate the difference between two systems from algorithm design, individual diversity and shape space. At the end of the paper, numerical experiment is used to test the performance of swarm intelligence techniques and AIS, where benchmark test functions include unimodal and multimodal function optimisation problems. Besides, combined with a concrete example, travelling salesman problem (TSP), the generality and feature of these two systems in solving complex problems are discussed in detail. The objective of the paper is to set up inherent connection and difference between two unlike systems, which not only has important theoretical significance but also has significant actual value to reveal production and operation mechanism of human intelligence.
Online publication date: Wed, 03-Apr-2013
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Bio-Inspired Computation (IJBIC):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email firstname.lastname@example.org